{"id":"https://openalex.org/W7161131589","doi":"https://doi.org/10.1145/3746467.3801501","title":"iGenOrch: Intelligent Orchestration Framework for Multi-Model LLM Inference on Edge Platforms","display_name":"iGenOrch: Intelligent Orchestration Framework for Multi-Model LLM Inference on Edge Platforms","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7161131589","doi":"https://doi.org/10.1145/3746467.3801501"},"language":null,"primary_location":{"id":"doi:10.1145/3746467.3801501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801501","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746467.3801501","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106504993","display_name":"Faiza Akram","orcid":null},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Faiza Akram","raw_affiliation_strings":["Mississippi State University, Starkville, MS, USA"],"raw_orcid":"https://orcid.org/0009-0000-7134-7405","affiliations":[{"raw_affiliation_string":"Mississippi State University, Starkville, MS, USA","institution_ids":["https://openalex.org/I99041443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136157100","display_name":"Maisha Rahman Chowdhury","orcid":"https://orcid.org/0009-0008-0693-8696"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maisha Rahman Chowdhury","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0008-0693-8696","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136093098","display_name":"Gabriella Dunne","orcid":"https://orcid.org/0009-0003-5285-9386"},"institutions":[{"id":"https://openalex.org/I108093660","display_name":"Benedictine College","ror":"https://ror.org/02fn4qf13","country_code":"US","type":"education","lineage":["https://openalex.org/I108093660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriella Dunne","raw_affiliation_strings":["Benedictine College, Atchison, USA"],"raw_orcid":"https://orcid.org/0009-0003-5285-9386","affiliations":[{"raw_affiliation_string":"Benedictine College, Atchison, USA","institution_ids":["https://openalex.org/I108093660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136091233","display_name":"Katherine Williams","orcid":"https://orcid.org/0009-0004-5660-3625"},"institutions":[{"id":"https://openalex.org/I184889055","display_name":"Washington and Lee University","ror":"https://ror.org/05r9xgf14","country_code":"US","type":"education","lineage":["https://openalex.org/I184889055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Williams","raw_affiliation_strings":["Washington and Lee University, Lexington, USA"],"raw_orcid":"https://orcid.org/0009-0004-5660-3625","affiliations":[{"raw_affiliation_string":"Washington and Lee University, Lexington, USA","institution_ids":["https://openalex.org/I184889055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093382336","display_name":"Kaleb Love","orcid":null},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaleb Love","raw_affiliation_strings":["Mississippi State University, Starkville, USA"],"raw_orcid":"https://orcid.org/0009-0003-6758-6982","affiliations":[{"raw_affiliation_string":"Mississippi State University, Starkville, USA","institution_ids":["https://openalex.org/I99041443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067899667","display_name":"Asad Waqar Malik","orcid":"https://orcid.org/0000-0003-3804-997X"},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asad Waqar Malik","raw_affiliation_strings":["Mississippi State University, Starkville, Mississippi, USA"],"raw_orcid":"https://orcid.org/0000-0003-3804-997X","affiliations":[{"raw_affiliation_string":"Mississippi State University, Starkville, Mississippi, USA","institution_ids":["https://openalex.org/I99041443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087785712","display_name":"Samee U. Khan","orcid":"https://orcid.org/0000-0001-8650-4354"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samee U. Khan","raw_affiliation_strings":["Kansas State University, Manhattan, USA"],"raw_orcid":"https://orcid.org/0009-0007-6641-9735","affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5106504993"],"corresponding_institution_ids":["https://openalex.org/I99041443"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88271617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.12160000205039978,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.10639999806880951,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6345000267028809},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6008999943733215},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5906000137329102},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5325999855995178},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.44369998574256897},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.43860000371932983},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.42170000076293945},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.40939998626708984},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.39969998598098755},{"id":"https://openalex.org/keywords/working-set","display_name":"Working set","score":0.3984000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500999808311462},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.44369998574256897},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C88196245","wikidata":"https://www.wikidata.org/wiki/Q8034984","display_name":"Working set","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C553261973","wikidata":"https://www.wikidata.org/wiki/Q14579","display_name":"Linux kernel","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C68694590","wikidata":"https://www.wikidata.org/wiki/Q267558","display_name":"Original equipment manufacturer","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C26324664","wikidata":"https://www.wikidata.org/wiki/Q1065525","display_name":"Message queue","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C4927394","wikidata":"https://www.wikidata.org/wiki/Q787631","display_name":"Business Process Execution Language","level":4,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746467.3801501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801501","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746467.3801501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801501","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2861205274","display_name":null,"funder_award_id":"CCF 213543","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4648694209","display_name":null,"funder_award_id":"CNS 1911012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6007355988","display_name":null,"funder_award_id":"CNS 2124908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4405794828"],"related_works":[],"abstract_inverted_index":{"The":[0,102,134],"growing":[1],"demand":[2],"for":[3,56,63,96],"on-device":[4],"Large":[5],"Language":[6],"Model":[7],"(LLM)":[8],"inference":[9],"has":[10],"accelerated":[11],"the":[12,64],"deployment":[13],"of":[14,40],"AI":[15],"capabilities":[16],"onto":[17],"constrained":[18,100],"edge":[19,79],"platforms.":[20],"However,":[21],"effective":[22],"resource":[23],"management":[24],"remains":[25],"a":[26,37,88,105,129,149],"critical":[27],"challenge,":[28],"especially":[29],"with":[30,36],"multiple":[31],"LLM":[32,162],"processes":[33],"run":[34],"concurrently":[35],"diverse":[38],"set":[39],"requirements":[41],"such":[42,112],"as":[43,113],"latency,":[44,115],"memory":[45,122,174],"footprints,":[46],"and":[47,59,67,74,121,144,153,157,176],"workload":[48,158],"patterns.":[49],"Traditional":[50],"Linux":[51],"kernel":[52,132],"schedulers":[53],"are":[54],"designed":[55],"general-purpose":[57],"workloads":[58,98],"fail":[60],"to":[61,147],"account":[62],"bursty,":[65],"compute-":[66],"memory-sensitive":[68],"LLMs,":[69],"resulting":[70],"in":[71],"unstable":[72],"latency":[73,156,171],"inefficient":[75],"CPU-memory":[76],"utilization":[77],"on":[78,99],"devices.":[80,101],"To":[81],"address":[82],"these":[83],"limitations,":[84],"we":[85],"propose":[86],"iGenOrch,":[87],"kernel-integrated":[89],"orchestration":[90],"framework":[91],"that":[92,108,167],"enables":[93],"intelligent":[94],"scheduling":[95],"multi-LLM":[97,181],"iGenOrch":[103,135,168],"incorporates":[104],"monitoring":[106],"module":[107],"captures":[109],"runtime":[110],"metrics,":[111],"per-request":[114],"queue":[116],"size,":[117],"token":[118],"throughput,":[119],"CPU,":[120],"usage.":[123],"This":[124],"is":[125],"fed":[126],"directly":[127],"into":[128],"modified":[130],"device":[131],"scheduler.":[133],"dynamically":[136],"adapts":[137],"CPU":[138],"affinity,":[139],"process":[140],"priority,":[141],"concurrency":[142],"levels,":[143],"batch":[145],"size":[146],"approximate":[148],"multi-objective":[150],"optimization":[151],"problem":[152],"achieves":[154],"lower":[155],"distribution":[159],"across":[160],"concurrent":[161,180],"instances.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"significantly":[169],"improves":[170,177],"stability,":[172],"reduces":[173],"overhead,":[175],"stability":[178],"under":[179],"execution.":[182]},"counts_by_year":[],"updated_date":"2026-05-15T06:12:33.780692","created_date":"2026-05-15T00:00:00"}